Cohere makes Tiny Aya Global, an open-weights chat model that takes and returns text.
Input
Output
Context
8K
Max Output
4K
Parameters
3.3B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
Measured speed: 131 tok/s output speed · 0.20 s to first answer token · 0.20 s to first token
Bands compare this model with every model the same suite measured in our catalog.
Download 6.70 GB · Runs on vLLM v0.32.0 · 11 GGUF builds
| Precision | Weights | One request at 8K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 6.24 GB | 7.31 GB | 1x NVIDIA T4 (16 GB) |
| INT8 | 3.12 GB | 4.04 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 1.56 GB | 2.40 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 3,349,227,520 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
Tiny Aya Global has a context window of 8,192 tokens and a maximum output of 4,000 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Tiny Aya Global is an open-weight model under the Cc by nc 4.0 license. You can download and self-host it within the license terms.
Tiny Aya Global has 3,349,227,520 parameters (3.3B), as stated in the creator's Hugging Face repository.
Strengths: The creator publishes GGUF builds; Supports 67 languages. Limitations: License does not allow commercial use (cc-by-nc-4.0); Short context window: 8,192 tokens; Below average on graduate-level science (GPQA) among measured models. Each is computed from the model's stated facts and benchmark results.
Tiny Aya Global accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
Tiny Aya Global has published results from Artificial Analysis. The Benchmarks card shows each score as reported, with its band among the models the same source measured. Scores are never combined across sources.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Tiny Aya Global, and Inferbase runs it on your account with the same routing and logs.
The weights take 6.2 GB at FP16 / BF16, 3.1 GB at INT8, 1.6 GB at INT4, computed from the 3,349,227,520 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
The model card of Tiny Aya Global lists 67 languages: English, Dutch, French, Italian, Portuguese, Romanian, Spanish, Czech, Polish, Ukrainian, Russian, Greek, German, Danish, Swedish, Norwegian, Catalan, Galician, Welsh, Irish, Basque, Croatian, Latvian, Lithuanian, Slovak, Slovenian, Estonian, Finnish, Hungarian, Serbian, Bulgarian, Arabic, Persian, Urdu, Turkish, Maltese, Hebrew, Hindi, Marathi, Bangla, Gujarati, Punjabi, Tamil, Telugu, Nepali, Filipino, Malay, Indonesian, Vietnamese, Javanese, Khmer, Thai, Lao, Chinese, Burmese, Japanese, Korean, Amharic, Hausa, Igbo, Malagasy, Shona, Swahili, Wolof, Xhosa, Yoruba and Zulu. That is what Cohere states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.